updated the How to use section so that the code actually does what the live demo does (#4)

- updated the How to use section so that the code actually does what the live demo does (199695c904a49dc957f737821c2ada065c8d4517)
- swtiched to YolosImageProcessor (bbd712b25cecec17f9a487f38096f55db7285a9f)


Co-authored-by: Srinivas Gorur-Shandilya <[email protected]>

README.md

@@ -35,22 +35,34 @@ You can use the raw model for object detection. See the [model hub](https://hugg
 Here is how to use this model:
 
 ```python
-from transformers import YolosFeatureExtractor, YolosForObjectDetection
+from transformers import YolosImageProcessor, YolosForObjectDetection
 from PIL import Image
+import torch
 import requests
 
-url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 
-feature_extractor = YolosFeatureExtractor.from_pretrained('hustvl/yolos-tiny')
 model = YolosForObjectDetection.from_pretrained('hustvl/yolos-tiny')
+image_processor = YolosImageProcessor.from_pretrained("hustvl/yolos-tiny")
 
-inputs = feature_extractor(images=image, return_tensors="pt")
+inputs = image_processor(images=image, return_tensors="pt")
 outputs = model(**inputs)
 
 # model predicts bounding boxes and corresponding COCO classes
 logits = outputs.logits
 bboxes = outputs.pred_boxes
+
+
+# print results
+target_sizes = torch.tensor([image.size[::-1]])
+results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+        f"Detected {model.config.id2label[label.item()]} with confidence "
+        f"{round(score.item(), 3)} at location {box}"
+    )
 ```
 
 Currently, both the feature extractor and model support PyTorch.